[hsa] Do not output an extraneous kernel when gridifying

[Martin Jambor]

Hi,

a small bug caused HSAIL output of a kernel for the parallel
construct, even when it has been made a part of a gridified kernel and
the standalone construct is therefore not necessary for HSA.  This
small patch fixes that.  Committed to the branch.
On a related note, I have merged trunk revision 228776 (just before
OpenMP 4.5 landed) to the branch and am in the process of
forward-porting the relevant bits to the new OpenMP.  Hopefully it
will not take too long.

Thanks,

Martin


2015-10-20  Martin Jambor  <mjam...@suse.cz>

        * omp-low.c (region_part_of_target_p): Renamed to
        region_needs_kernel_p, return false for parts of gridified kernels.
        (expand_parallel_call): Adjusted.
---
 gcc/omp-low.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index 56cc813..900ed19 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -4872,19 +4872,32 @@ gimple_build_cond_empty (tree cond)
   return gimple_build_cond (pred_code, lhs, rhs, NULL_TREE, NULL_TREE);
 }
 
-/* Return true if the REGION is within a declare target function or within a
-   target region.  */
+/* Return true if a parallel REGION is within a declare target function or
+   within a target region and is not a part of a gridified kernel.  */
 
 static bool
-region_part_of_target_p (struct omp_region *region)
+region_needs_kernel_p (struct omp_region *region)
 {
+  bool indirect = false;
+  for (region = region->outer; region; region = region->outer)
+    {
+      if (region->type == GIMPLE_OMP_PARALLEL)
+       indirect = true;
+      else if (region->type == GIMPLE_OMP_TARGET)
+       {
+         gomp_target *tgt_stmt;
+         tgt_stmt = as_a <gomp_target *> (last_stmt (region->entry));
+         if (tgt_stmt->kernel_iter)
+           return indirect;
+         else
+           return true;
+       }
+    }
+
   if (lookup_attribute ("omp declare target",
                        DECL_ATTRIBUTES (current_function_decl)))
     return true;
 
-  for (region = region->outer; region; region = region->outer)
-    if (region->type == GIMPLE_OMP_TARGET)
-      return true;
   return false;
 }
 
@@ -5058,7 +5071,7 @@ expand_parallel_call (struct omp_region *region, 
basic_block bb,
                            false, GSI_CONTINUE_LINKING);
 
   if (hsa_gen_requested_p ()
-      && region_part_of_target_p (region))
+      && region_needs_kernel_p (region))
     {
       cgraph_node *child_cnode = cgraph_node::get (child_fndecl);
       hsa_register_kernel (child_cnode);
-- 
2.6.0